© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12405
    Prev
    Next
    INDEX
    Explanations

    technical writing about a sprayable chemical substance

    oai_token-act-pair · gemini-2.0-flash

    spray

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spray
    -1.66
    Spray
    -1.65
    spray
    -1.59
     Spray
    -1.56
     spraying
    -1.45
     sprayed
    -1.36
     sprays
    -1.35
     sprayer
    -0.94
     apply
    -0.88
     Apply
    -0.84
    POSITIVE LOGITS
     bomb
    0.57
    igin
    0.53
     bombs
    0.49
     démo
    0.49
     Rift
    0.48
    umbu
    0.47
    Giá
    0.47
    numRows
    0.47
    onOptions
    0.47
     OMITBAD
    0.46
    Activations Density 3.710%

    No Known Activations